A5101821280- Tactile and Sensory Interactions
- Electric Power System Optimization
- Advanced Malware Detection Techniques
- Remote Sensing in Agriculture
- Complex Network Analysis Techniques
- Human Pose and Action Recognition
- AI in cancer detection
- Gaze Tracking and Assistive Technology
- Industrial Vision Systems and Defect Detection
- Remote Sensing and LiDAR Applications
- Hand Gesture Recognition Systems
- Market Dynamics and Volatility
- Cryptography and Data Security
- Diabetic Foot Ulcer Assessment and Management
- Fire effects on ecosystems
- Privacy-Preserving Technologies in Data
- Advanced Graph Neural Networks
- Digital Media Forensic Detection
- Energy Load and Power Forecasting
- EEG and Brain-Computer Interfaces
- User Authentication and Security Systems
- Gait Recognition and Analysis
- Advanced Clustering Algorithms Research
Jinan University
2022
University High School
2020-2022
Rensselaer Polytechnic Institute
2021
Tsinghua University
2016
When the solution domain, internal parameters, and initial boundary conditions of partial differential equation (PDE) are changed, many potential characteristics equation’s solutions still similar. This provides possibility to reduce cost PDE operator learning through transfer methods. Based on Fourier neural (FNO), we propose a novel sparse network named λ-FNO. By introducing λ parameter matrix using new pruning method make sparse, ability λ-FNO is greatly improved. Using can efficiently...
Gait recognition, a task of identifying people through their walking pattern, has attracted more and researchers' attention. At present, most skeleton-based gait recognition approaches extract features from merely joint coordinates. However, the information, e.g. bone motion, is equally instructive discriminative for recognition. Thus, this paper proposes novel multi-stream part-fused graph convolutional network, MS-Gait, to fuse part-level information capture multi-order skeleton data. To...
In this paper, we propose a novel categorization framework to recognize tactile sequences based on two particular properties of the data. For first one, are spatio-temporal data which is sequential and dynamic, depicting process grasping an object in different stages; therefore, it reasonable discover dynamical pattern by modeling as integral rather than individual frames. second sequence contains various patterns stages process; decompose whole into multiple mini-sequences so enhance...
In recent decades, with the rapid development of society, people's quality life has improved, but incidence diseases such as diabetes become more and serious. According to authoritative literature, occurrence may be related a person's age, living environment, habits, genes, past medical history other factors. We can get accurate models through machine learning training on large amount data, in order protect patients' private information between different hospitals, it is impossible conduct...
Abstract CAPTCHAs are automated tests designed to distinguish between humans and computers. They could be easily solved by humans, but they become challenging for machines solve, therefore preventing programs from abusing online services occupying internet resources. Using Convolutional Neural Networks, the CAPTCHA automatically at high efficiency. Current approaches of accuracy recognition can structurally complicated. As a result, our team explored different approach solve using Network...
In part due to climate change, the last few years have been some of warmest on record and characterized by hot dry weather. This led a frequent outbreak wildfires, especially in already areas such as California. Experiments were conducted evaluate ability machine learning models detect wildfires map burnt using satellite images. For detection different complexities are trained distinguish between images containing no wildfires. The tested achieved consistently training accuracies above 90%...